#!/usr/bin/perl my @t = ("A\x{300}B", # U+0300 GRAVE ACCENT "AA", "A\x{41}\x{300}", # U+0041 LATIN CAPITAL LETTER A "\x{55}\x{308}O", # U+0308 COMBINING DIAERESIS "\x{dc}U" # U+00DC capital U with DIAERESIS ); binmode(STDOUT, ':utf8'); for (@t) { print "MATCH: $_\n" if /\p{Lu}{2}/; }